Vectara REST API

Computes the amount of quota consumed across the entire Vectara account. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2).

Computes the amount of quota consumed by a corpus. This capability is useful for administrators to track and monitor the amount of usage for specific corpora. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.

This API is intended to be used by experts. It gives you fine-grained control over chunking strategies by using the `parts`. Most users will want to use the [File Upload API](https://docs.vectara.com/docs/rest-api/file-upload) or the "standard" [Index API](https://docs.vectara.com/docs/rest-api/index). Some tips for this API: * This operation authenticates with either the Personal API Key, Index API Key, or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * The `metadataJson` object needs the JSON to be escaped so that it's not confused with other parts of the request JSON. * [Custom dimensions](https://docs.vectara.com/docs/learn/semantic-search/add-custom-dimensions) (`customDims`) is a feature that is only available to [Scale](https://vectara.com/pricing/) accounts.

Creates an API key that you bind with a specific corpus or multiple corpora. You can create an API key that only gives access to query data (read-only) or an API key that gives access to both querying and serving (read-write). Some tips for this API: * This operation only works with OAuth 2.0 (in a JWT "Bearer Token") authentication. It does not work with API Keys. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2).

Creates a corpus, which is a container to store data in. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `name` of the corpus is the only required field. * Filter attributes tell Vectara which metadata fields you'd like to run SQL-style filters against. If you need to change them after you've created the corpus, see the [Replace Filter Attributes API](https://docs.vectara.com/docs/rest-api/replace-corpus-filter-attrs) * `textless` and `customDimensions` are features that are only available to [Scale](https://vectara.com/pricing/) accounts.

Delete documents from a corpus. Some tips for this API: * This operation authenticates with either the Personal API Key, Index API Key, or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * You can quickly delete all documents from a corpus to clear it out by using the [Reset Corpus](https://docs.vectara.com/docs/rest-api/reset-corpus) operation.

Deletes API keys to help you manage the security and lifecycle of API keys in your application. Some tips for this API: * This operation only works with OAuth 2.0 (in a JWT "Bearer Token") authentication. It does not work with API Keys. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2).

Delete conversations from the chat history corpus. This is useful for data management to help ensure that you maintain data hygiene and support compliance with data retention policies. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access).

Deletes a corpus and all of the data contained inside of the corpus. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * It can take a few seconds to completely delete the corpus if there's heavy system load. Be patient if the corpus is still present after a deletion request is initiated.

Deletes specific turns from a conversation within the chat history corpus. This enables developers to remove inaccurate or inappropriate responses from the conversation history. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access).

Disables specific turns from a conversation within the chat history corpus. This is useful for excluding specific turns from a conversation. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access).

Enables or disables a specific API key. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2).

The File Upload API can be used to index binary files like PDFs, Word Documents, and similar. Vectara will attempt to automatically extract the text and any metadata from the document like author or title, though you can provide additional metadata as well. Some tips for this API: * This operation authenticates with either the Personal API Key, Index API Key, or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * You can find a full list of supported file formats [here](https://docs.vectara.com/docs/api-reference/indexing-apis/file-upload/file-upload-filetypes). * To provide additional metadata, set the `doc_metadata` field. You can find some additional details [here](https://docs.vectara.com/docs/api-reference/indexing-apis/file-upload/file-upload#attach-additional-metadata) * PDFs must contain text: Vectara does not currently support indexing scanned images via OCR. * There is a known issue with the OpenAPI plugin where the generated Python script for file uploads incorrectly uses placeholder values for the file path and filename. Manually replace '/path/to/file' and 'file' in the files array with the actual file path and filename.

Displays usage information about indexing and query operations in a corpus. This helps administrators in analyzing and managing resource consumption more efficiently for specific corpora. Some tips for this API: * Use these metrics to determine usage patterns that enable you to optimize resource allocations. * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.

This is the "standard" Indexing API for indexing semi-structured, text-heavy "documents." Indexing data into Vectara is typically very fast: within a few seconds. Some tips for this API: * This operation authenticates with either the Personal API Key, Index API Key, or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * Vectara does require a special format for JSON objects you'd like to index. Some tips on how to model data in the indexing API, see the documentation [here](https://docs.vectara.com/docs/learn/document-data-structuring). * The `metadataJson` object needs the JSON to be escaped so that it's not confused with other parts of the request JSON. * [Custom dimensions](https://docs.vectara.com/docs/learn/semantic-search/add-custom-dimensions) (`customDims`) is a feature that is only available to [Scale](https://vectara.com/pricing/) accounts.

Lists the API keys and the associated corpora names and IDs. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.

List all the conversations in a specific corpus. This data enables developers to monitor chatbot interactions and understand how users engage with the data. Pagination lets developers navigate through large datasets. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access).

Lists all corpora accessible to the OAuth client. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.

Lists information about each document ingested into the corpus including the Document ID and metadata. This is useful for managing the lifecycle of documents and a quick way to check which documents are already in the index. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2).

List the jobs associated with this account. Jobs are background processes like [replacing the filterable metadata attributes](https://docs.vectara.com/docs/rest-api/replace-corpus-filter-attrs). Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * It's best practice to filter as much as possible (by date, by status, and/or by job ID) to make job lists as easy to interpret as possible, as there can be many for a given time window.

Lists the users in your account along with their corpus access and customer-level authorizations. Some tips for this API: * This operation only works with OAuth 2.0 (in a JWT "Bearer Token") authentication. It does not work with API Keys. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * Use this API to view the members on your team. If you need to manage their access, use the Manage User endpoint.

Lets you manage users in your account by adding, deleting, enabling, or disabling users. You can also reset their passwords and edit user roles. This endpoint can help you streamline your onboarding process by programmatically adding new users, assigning appropriate roles, and setting up permissions. Some tips for this API: * This operation only works with OAuth 2.0 (in a JWT "Bearer Token") authentication. It does not work with API Keys. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * Add multiple users by including additional “user” objects into the userAction array.

Search for relevant results, highlight relevant snippets, and do [Retrieval Augmented Generation](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview) (RAG). Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * By default, Vectara only uses its neural/semantic retrieval model, and does not attempt to use keyword matching. To enable hybrid search with a mix of both keyword and neural results, edit the `lambda` value. Additional documentation on hybrid search is [here](https://docs.vectara.com/docs/learn/semantic-search/hybrid-search). * Vectara can automatically provide a generative summary with the query results for Retrieval Augmented Generation (RAG). Additional details on RAG in Vectara can be found [here](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview). * The Query API takes an *array* of queries, since you can have Vectara perform more than 1 query in a single API call. The results that are returned are thus in an array as well, with each element in the response array corresponding to the input query array. * Custom dimensions (the `dim` array) is a feature that is only available to [Scale](https://vectara.com/pricing/) accounts. * Reranking enhances search accuracy and variety and more details can be found [here](https://docs.vectara.com/docs/api-reference/search-apis/reranking).

Retrieves detailed information about specific conversations. This information enables developers to analyze the flow of user chats and understand the context of interactions, which helps in refining chatbot responses. You can read up to 100 conversations. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access).

Displays detailed information about corpora within your account including basic information, metadata, and whether it is enabled or disabled. This endpoint can help administrators monitor the amount of quota consumed by tenants. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.

Updates the filterable metadata fields for the corpus. See our documentation on [filterable metadata fields](https://docs.vectara.com/docs/learn/metadata-search-filtering/filter-overview) for more details on how these are used. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * Each request to replace the corpus filter attributes kicks off a background [job](https://docs.vectara.com/docs/rest-api/list-jobs). The job ID is returned when you kick off a metadata filter update job so you can track it later. * Existing filters will continue to apply until the update job completes. * The time that update filter jobs take is roughly proportional to the size of the corpus. Updates on small corpora generally take a few minutes at most, but updates on large corpora can take many minutes to hours to complete.

Resets a corpus by removing all of the documents inside of it. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus. * If you want to delete individual documents instead of all documents in the corpus, you can use the [Delete API](https://docs.vectara.com/docs/rest-api/delete).

Stream responses as you search for relevant results, highlight relevant snippets, and do [Retrieval Augmented Generation](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview) (RAG). Instead of receiving a complete response like with the Standard Query API, you receive partial responses in this order: 1. Search results. 2. If summarization is enabled, you get chunks of the summary, like "This", "is", "a", "summary". 3. If FCS is enabled, then the FCS is the final response. Some tips for this API: * This operation authenticates with either an API Key or OAuth 2.0 (in a JWT "Bearer Token"). You can find details of how to set up an API key or use OAuth 2.0 [here](https://docs.vectara.com/docs/console-ui/manage-api-access). * The Query API takes an *array* of queries, since you can have Vectara perform more than 1 query in a single API call. The results that are returned are thus in an array as well, with each element in the response array corresponding to the input query array. * Custom dimensions (the `dim` array) is a feature that is only available to [Scale](https://vectara.com/pricing/) accounts. * Reranking enhances search accuracy and variety and more details can be found [here](https://docs.vectara.com/docs/api-reference/search-apis/reranking).

Lets you enable or disable a corpus. This is useful when you need to take the corpus offline without having to delete the corpus. Some tips for this API: * This operation works with the Personal API Key and OAuth 2.0 (in a JWT "Bearer Token") authentication. You can find details of how to set up and use OAuth 2.0 [here](https://docs.vectara.com/docs/deploy-and-scale/authentication/oauth-2). * The `filter` feature applies to either the name *or* the description of a corpus.